grok-routing

grok-routing is a skill for Claude Code from kai-wedekind/claude-code-grok-bridge. It costs 92 tokens per session (1,383 once invoked), scanned A, original, Apache-2.0.

A set of rules for deciding when coding work should be done with Grok Build, an AI coding service, instead of directly in Claude Code. It covers manual requests, second opinions, delegation, and implementation work.

In plain words
What is it for?
It helps choose how to review code, get another opinion, run work through Grok, delegate implementation, inspect runs, or stop an active task.
Why use it?
It prevents the agent from sending work elsewhere without permission and makes the trade-offs around cost, risk, and control explicit.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: mentions CLAUDE.md; positional $N argument; mentions Claude Code.

Part of the grok-build plugin — 3 skills, 7 commands, 1 agent, 2 hooks shipped together

Good fit It helps choose how to review code, get another opinion, run work through Grok, delegate implementation, inspect runs, or stop an active task.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/kai-wedekind/claude-code-grok-bridge/grok-routing
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add kai-wedekind/claude-code-grok-bridge --skill grok-routing
Clone the repo
git clone --depth 1 https://github.com/kai-wedekind/claude-code-grok-bridge

Made for: Claude Code.

Or install grok-build, the plugin that ships this one along with the rest of its 3 skills, 7 commands, 1 agent, 2 hooks.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for grok-routing

README.md
[![agentmods](https://agentmods.dev/badge/skills/kai-wedekind/claude-code-grok-bridge/grok-routing/github.svg)](https://agentmods.dev/skills/kai-wedekind/claude-code-grok-bridge/grok-routing)
Your own site
<a href="https://agentmods.dev/skills/kai-wedekind/claude-code-grok-bridge/grok-routing"><img src="https://agentmods.dev/badge/skills/kai-wedekind/claude-code-grok-bridge/grok-routing/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for grok-routing

Your own site · 80×15
<a href="https://agentmods.dev/skills/kai-wedekind/claude-code-grok-bridge/grok-routing"><img src="https://agentmods.dev/badge/skills/kai-wedekind/claude-code-grok-bridge/grok-routing.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 92 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,383 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00092 $0.01383
Opus 5 $0.00046 $0.00691
Sonnet 5 $0.00018 $0.00277
Haiku 4.5 $0.00009 $0.00138

Measured 10d ago against content hash d38096b1581b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

grok-routing scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 10d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

plugins/grok-build/skills/grok-routing/SKILL.md · 81 lines

How it starts

The opening of the file, as written. The whole thing — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.

When to reach for Grok Build

Installing this plugin gives Claude Code the ability to use Grok. It does not give it an occasion. Seven slash commands sit there until somebody types one, and the only thing that fires by itself is the grok-delegate agent's description — which covers being stuck and wanting a second implementation pass, and nothing else.

That gap is deliberate: how much of your work should leave your machine is your decision, not this plugin's. This skill is the menu; your CLAUDE.md picks a dish.

Reading your own setting

Your project or user CLAUDE.md should carry one line naming a tier. If it does not, the tier is manual — do not offload anything the user did not ask for.

If it names a tier you do not recognise, ask rather than guess. A wrong guess here spends somebody's paid allowance.

The tiers

Each is a superset of the one above it. Risk and reach grow together, and so does spend.

manual — nothing automatic

Slash commands only: /grok-build:review, /grok-build:critique, /grok-build:delegate, /grok-build:runs, /grok-build:stop, and the rest. Never route work to Grok on your own initiative. This is the default and the right starting point.

second-opinion — independent eyes on finished work

Send completed work out for review, critique or verification. Read-only, always.

The value here is not that Grok is better; it is that it is not you. It did not choose the approach, did not write the test, and does not know which parts you were confident about. That is the whole reason a second pass finds anything.

Good moments: after a non-trivial change and before declaring it done; when a fix touches a path that is hard to test; when you have just written the test that proves your own fix.

A verifier that only reads your summary is worthless. Give it the diff and the commits, tell it what you claim, and ask it to disagree. If it comes back agreeing with everything, suspect the prompt before believing the verdict.

Read the full file on GitHub · 81 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 10d ago First seen · 81 lines · 92 tokens per session scan A d38096b1581b

Subscribe to this mod's changes

grok-routing is a skill published in the GitHub repository kai-wedekind/claude-code-grok-bridge (2 stars, last pushed 19d ago), licensed Apache-2.0. It adds 92 tokens to every session and 1,383 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

taiyi-integration

A project workflow skill for closing a TaiyiForge change and recording it in a CHANGELOG.md file. It checks review results, tests, and the state of the working tree before archiving the change.

Dong90/oh-my-taiyiforge · 27 tokens

taiyi-requirement

A requirements-analysis process that turns a proposed change into a REQUIREMENT.md document. It records user needs, acceptance checks, terminology, triggers, and dependencies, with different levels of detail for different project sizes.

Dong90/oh-my-taiyiforge · 27 tokens

taiyi-change

A TaiyiForge workflow stage for writing a change proposal in CHANGE.md, with checks for scope, risks, success criteria, and related project documents.

Dong90/oh-my-taiyiforge · 25 tokens

taiyi-test

A project workflow skill for verifying an implementation and producing a TEST.md record. TDD means writing a failing test, implementing the change, and then making the test pass; this skill checks that process and other regression cases.

Dong90/oh-my-taiyiforge · 24 tokens

taiyi-ui-design

A design-planning guide for describing how an application's user interface should look and behave. It produces a UI-DESIGN.md document covering layouts, components, interactions, accessibility, and error states.

Dong90/oh-my-taiyiforge · 35 tokens

taiyi-diagram-flow

A TaiyiForge diagramming skill that turns requirements and designs into Mermaid workflow diagrams. Mermaid is a text format for drawing flowcharts, API call sequences, and state changes.

Dong90/oh-my-taiyiforge · 44 tokens